Just make sure you completely understand the code that AI gives you, never
use it blindly.

--------------------------------------------------------------
Carl J. Nobile (Software Engineer/API Design)
[email protected]
--------------------------------------------------------------

On Mon, Aug 10, 2026, 10:38 AM jonathan hunsberger via TriEmbed <
[email protected]> wrote:

> I use this at work and it's better than I am at coding. I still don't use
> it for personal things because there the whole point is the activity itself
> and the experience gained. Important distinction I think. If you just want
> to get it done, use an LLM. If you want to *do* it, do it yourself.
>
>
>
> On Mon, Aug 10, 2026, 08:24 Trampas Stern via TriEmbed <
> [email protected]> wrote:
>
>> If you want to have some fun, ask AI to review the code, or add a
>> feature.   It is not perfect but it is really good.
>>
>> Trampas
>>
>> On Sun, Aug 9, 2026 at 11:39 PM John Wettroth <[email protected]>
>> wrote:
>>
>>> Wow- Trampass recommended that I throw the mess at AI and it worked.  Its
>>> was like working with a sharp programmer sitting next to me.
>>>
>>>
>>>
>>> Really learned something!  I would never, ever have found the problem.
>>>
>>>
>>>
>>> Regards,
>>> John M. Wettroth
>>>
>>> E: [email protected]
>>> M: (919) 349-9875
>>> H:  (984) 329-5420
>>>
>>>
>>>
>>> *From:* Trampas Stern <[email protected]>
>>> *Sent:* Sunday, August 9, 2026 5:21 PM
>>> *To:* jwet <[email protected]>
>>> *Subject:* Re: [TriEmbed] Stuck on a problem, firmware update on a
>>> cheap Geiger counter using STM Link
>>>
>>>
>>>
>>> So I started with copilot in visual studio code. Basically I opened
>>> directory with vscode then opened copilot in vscode and asked.
>>>
>>>
>>>
>>> Many start by installing Claude code or codex on their computer.
>>>
>>>
>>>
>>> For example when I set up a Linux box I install Claude code and then
>>> have it do the work.
>>>
>>>
>>>
>>> Note I gave a class at work 6 months ago and showed how to make a
>>> Pac-Man clone running using Web assemble with code in C in less than 30
>>> min. Then showed that in around 30 mins you can have duke nukem running in
>>> browser.
>>>
>>>
>>>
>>> AI is so powerful I have not written any code in 9 months.
>>>
>>>
>>>
>>> I even took Altium to AI to make it work in Wine on Linux. Fixed all the
>>> bugs in wine, and some in Altium by reverse engineering code.
>>>
>>>
>>>
>>> Basically install AI and ask it like you were talking to a college
>>> graduate you wanted to some work...
>>>
>>>
>>>
>>> Trampas
>>>
>>>
>>>
>>> On Sun, Aug 9, 2026, 5:07 PM John Wettroth <[email protected]> wrote:
>>>
>>> Can you give me a little guidance.  Do I Just go to a chat gpt prompt
>>> and start explaining and show my console stuff?  I’m not up on this.
>>> Thanks.
>>>
>>>
>>>
>>> Regards,
>>> John M. Wettroth
>>>
>>> E: [email protected]
>>> M: (919) 349-9875
>>> H:  (984) 329-5420
>>>
>>>
>>>
>>> *From:* Trampas Stern <[email protected]>
>>> *Sent:* Sunday, August 9, 2026 5:05 PM
>>> *To:* jwet <[email protected]>
>>> *Subject:* Re: [TriEmbed] Stuck on a problem, firmware update on a
>>> cheap Geiger counter using STM Link
>>>
>>>
>>>
>>> Did you copy into AI and ask it. You most likely can have AI even
>>> program the device and debug why it fails.
>>>
>>>
>>>
>>> Trampas
>>>
>>>
>>>
>>> On Sun, Aug 9, 2026, 4:55 PM John Wettroth via TriEmbed <
>>> [email protected]> wrote:
>>>
>>> This is a help request, must be rusty on my firmware updating skills.  I
>>> bought
>>> a cheap Geiger counter on Ebay (GC2011) for $20- they're normally about
>>> $50, but
>>> this was lightly used and unwanted.  I used to design Radiation
>>> Monitoring stuff
>>> for the first 10 years of my career and thought having one of these
>>> around would
>>> be fun.  These are reasonable quality hardware with a GM tube, graphics
>>> display
>>> and little ARM CPU.  My unit has a monochrome LCD, others by Fnisri and
>>> Boser
>>> have color LCD's and look better.  They all share a pretty common
>>> design.  The
>>> hardware isn't bad but the firmware is not very good.  Someone reverse
>>> engineered and posted a replacement firmware on GitHub- called Radpro.
>>> Its open
>>> source, multilanguage, very will done code.  Full source is on Git along
>>> with
>>> binary images for different models.  I took this easy route.  I found
>>> the right
>>> version of code, got out my STMLink dongle and followed the
>>> instructions.  The
>>> poster was trying to make things easy for non-programmers, so he wrapped
>>> some
>>> standard OCD stuff in batch or sh files to make it a simple command line
>>> launch.
>>> The unit doesn't have a boot loader, you use SWD mode though this
>>> script.  I'm
>>> having no luck- it starts well and then bombs out with an obscure
>>> error.  The
>>> console traffic (command.com session) is as follow after lunching the
>>> batch file
>>> per the instruction in the director where the bin file is located.  You
>>> make a
>>> choice of language and it does the rest.  I've posted on the Git and get
>>> no
>>> response.  It's a low traffic GIT that was more active a few years ago.
>>> I found
>>> out about the firmware from a Hockaday article by Al Williams.  Enough
>>> background.  Any help greatly appreciated.
>>>
>>> >>> Console Traffic after running "install.bat" from prompt while
>>> located in
>>> proper directory for my variant/bin file, things seem to go well until
>>> they
>>> don't
>>>
>>> Available language codes: bg cs da de el en es fi fr hr hu id it ja ko
>>> lt lv
>>> no pl pt ro ru sk sl sv tr uk vi zh_CN
>>> Enter language code for Rad Pro installation: en
>>> "..\fs2011-gd32f150c8\firmware\radpro-fs2011-gd32f150c8-en-3.1.1.bin"
>>> Backing up old firmware image...
>>> xPack Open On-Chip Debugger 0.12.0+dev-01850-geb6f2745b-dirty
>>> (2025-02-07-10:
>>>
>>> Licensed under GNU GPL v2
>>> For bug reports, read
>>>         http://openocd.org/doc/doxygen/bugs.html
>>> DEPRECATED: OpenOCD support for ST-Link HLA transport will be dropped
>>> soon!
>>> Consider updating your ST-Link firmware to a version >= V2J24 (2015)
>>> Info : auto-selecting first available session transport "hla_swd". To
>>> overrid
>>> se 'transport select <transport>'.
>>> Info : The selected transport took over low-level target control. The
>>> results
>>> ght differ compared to plain JTAG/SWD
>>> Info : clock speed 1000 kHz
>>> Info : STLINK V2J42S7 (API v2) VID:PID 0483:3748
>>> Info : Target voltage: 3.322828
>>> Info : [stm32f1x.cpu] Cortex-M3 r2p1 processor detected
>>> Info : [stm32f1x.cpu] target has 6 breakpoints, 4 watchpoints
>>> Info : [stm32f1x.cpu] Examination succeed
>>> Info : [stm32f1x.cpu] starting gdb server on 3333
>>> Info : Listening on port 3333 for gdb connections
>>> [stm32f1x.cpu] halted due to debug-request, current mode: Thread
>>> xPSR: 0x01000000 pc: 0x08007224 msp: 0x20002000
>>> Flashing new firmware image...
>>> xPack Open On-Chip Debugger 0.12.0+dev-01850-geb6f2745b-dirty
>>> (2025-02-07-10:
>>>
>>> Licensed under GNU GPL v2
>>> For bug reports, read
>>>         http://openocd.org/doc/doxygen/bugs.html
>>> DEPRECATED: OpenOCD support for ST-Link HLA transport will be dropped
>>> soon!
>>> Consider updating your ST-Link firmware to a version >= V2J24 (2015)
>>> Info : auto-selecting first available session transport "hla_swd". To
>>> overrid
>>> se 'transport select <transport>'.
>>> Info : The selected transport took over low-level target control. The
>>> results
>>> ght differ compared to plain JTAG/SWD
>>> Info : clock speed 1000 kHz
>>> Info : STLINK V2J42S7 (API v2) VID:PID 0483:3748
>>> Info : Target voltage: 3.295354
>>> Info : [stm32f1x.cpu] Cortex-M3 r2p1 processor detected
>>> Info : [stm32f1x.cpu] target has 6 breakpoints, 4 watchpoints
>>> Info : [stm32f1x.cpu] Examination succeed
>>> Info : [stm32f1x.cpu] starting gdb server on 3333
>>> Info : Listening on port 3333 for gdb connections
>>> [stm32f1x.cpu] halted due to debug-request, current mode: Thread
>>> xPSR: 0x01000000 pc: 0x08007224 msp: 0x20002000
>>> Info : device id = 0x13030410
>>> Info : flash size = 64 KiB
>>> [stm32f1x.cpu] halted due to debug-request, current mode: Thread
>>> xPSR: 0x01000000 pc: 0xfffffffe msp: 0xfffffffc
>>> ** Programming Started **
>>> Error: timed out while waiting for target halted
>>> [stm32f1x.cpu] halted due to debug-request, current mode: Handler
>>> HardFault
>>> xPSR: 0x01000003 pc: 0x08007274 msp: 0x20001fe0
>>> Error: error waiting for target flash write algorithm
>>> Error: error writing to flash at address 0x08000000 at offset 0x00000000
>>> embedded:startup.tcl:1819: Error: ** Programming Failed **
>>> Traceback (most recent call last):
>>>   File "embedded:startup.tcl", line 1884, in program
>>>     program_error {** Programming Failed **} 0
>>>   File "embedded:startup.tcl", line 1819, in program_error
>>>     error {** Programming Failed **}
>>> Press any key to continue .
>>>
>>>
>>> Thanks for your time.
>>>
>>> Regards,
>>> John M. Wettroth
>>> E: [email protected]
>>> M: (919) 349-9875
>>> H:  (984) 329-5420
>>>
>>>
>>>
>>> _______________________________________________
>>> Triangle, NC Embedded Interest Group mailing list
>>>
>>> To post message: [email protected]
>>> List info:
>>> http://mail.triembed.org/mailman/listinfo/triembed_triembed.org
>>> TriEmbed web site: https://TriEmbed.org
>>> To unsubscribe, click link and send a blank message: mailto:
>>> [email protected]?subject=unsubscribe
>>> Searchable email archive available at
>>> https://www.mail-archive.com/[email protected]/
>>>
>>> _______________________________________________
>> Triangle, NC Embedded Interest Group mailing list
>>
>> To post message: [email protected]
>> List info:
>> http://mail.triembed.org/mailman/listinfo/triembed_triembed.org
>> TriEmbed web site: https://TriEmbed.org
>> To unsubscribe, click link and send a blank message: mailto:
>> [email protected]?subject=unsubscribe
>> Searchable email archive available at
>> https://www.mail-archive.com/[email protected]/
>>
>> _______________________________________________
> Triangle, NC Embedded Interest Group mailing list
>
> To post message: [email protected]
> List info: http://mail.triembed.org/mailman/listinfo/triembed_triembed.org
> TriEmbed web site: https://TriEmbed.org
> To unsubscribe, click link and send a blank message: mailto:
> [email protected]?subject=unsubscribe
> Searchable email archive available at
> https://www.mail-archive.com/[email protected]/
>
>
_______________________________________________
Triangle, NC Embedded Interest Group mailing list

To post message: [email protected]
List info: http://mail.triembed.org/mailman/listinfo/triembed_triembed.org
TriEmbed web site: https://TriEmbed.org
To unsubscribe, click link and send a blank message: 
mailto:[email protected]?subject=unsubscribe
Searchable email archive available at 
https://www.mail-archive.com/[email protected]/

Reply via email to